Python Developer (AI & LLMs)

SPACE AI; Delray Beach (FL); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive salary

Remote work options

Professional development

Job summary

SPACE AI is seeking an AI/ML engineer to build end-to-end RAG pipelines for context-aware AI responses and to optimize large language model inference with vLLM. You will collaborate with ML engineers to deploy transformer models and work with graph databases like Neo4j.

The role emphasizes scalable data architectures, Python-based microservices, and cloud/containerization skills to enable low-latency AI systems in production.

Qualifications

• Proficiency in Python and AI/ML libraries (PyTorch, TensorFlow, Hugging Face Transformers).
• Hands-on experience with graph databases, especially Neo4j (Cypher queries, graph algorithms).
• Demonstrated work on RAG pipelines (retrieval, reranking, generation) using LangChain or LlamaIndex.
• Experience with vLLM or similar LLM optimization tools (quantization, distributed inference).
• Knowledge of vector databases (e.g., FAISS, Pinecone) and embedding techniques.
• Familiarity with cloud platforms (AWS/GCP/Azure) and containerization (Docker, Kubernetes).

Responsibilities

• Build end-to-end RAG (Retrieval-Augmented Generation) pipelines for context-aware AI responses.
• Implement and fine-tune vLLM for efficient inference of large language models (LLMs).
• Collaborate with ML engineers to deploy transformer models and vector databases.

Skills

Python

ML libraries

RAG pipelines

vLLM

Graph databases

Neo4j

APIs

Docker/Kubernetes

Cloud platforms

MLflow

Tools

LangChain

LlamaIndex

PyTorch

TensorFlow

Transformers

FAISS

Pinecone

FastAPI

Flask

Neo4j Cypher

Job description

Key Responsibilities

• Build end-to-end RAG (Retrieval-Augmented Generation) pipelines for context-aware AI responses.
• Implement and fine-tune vLLM for efficient inference of large language models (LLMs).
• Collaborate with ML engineers to deploy transformer models (e.g., BERT, GPT variants) and vector databases.

Data & Database Architecture

• Architect and optimize graph database systems (Neo4j) to model project knowledge networks and relationships.
• Develop Python-based microservices for data ingestion, processing, and API integrations (FastAPI, Flask).

Performance & Operations

• Monitor system performance, conduct A/B tests, and ensure low-latency responses in production.
• Ensure scalability and efficiency of AI systems.

Requirements

• Proficiency in Python and AI/ML libraries (PyTorch, TensorFlow, Hugging Face Transformers).
• Hands-on experience with graph databases, especially Neo4j (Cypher queries, graph algorithms).
• Demonstrated work on RAG pipelines (retrieval, reranking, generation) using frameworks like LangChain or LlamaIndex.
• Experience with vLLM or similar LLM optimization tools (quantization, distributed inference).
• Knowledge of vector databases (e.g., FAISS, Pinecone) and embedding techniques.
• Familiarity with cloud platforms (AWS/GCP/Azure) and containerization (Docker, Kubernetes).

Preferred Qualifications

• Strong experience with FastAPI or Flask for building high-performance APIs.
• Familiarity with MLOps principles and tools (e.g., MLflow, Kubeflow).
• Contributions to open-source AI/ML projects.
• Experience in performance tuning and A/B testing for AI systems in a production environment.

Soft Skills

• Strong analytical and problem-solving skills.
• Excellent communication and team collaboration abilities.
• Self-motivated with the ability to work independently and as part of a team.

What We Offer

• Competitive salary and performance-based bonuses.
• Flexible working hours with remote work options.
• Opportunities for professional development and skill enhancement.
• Collaborative and inclusive work environment.
• Paid sick time
• Paid time off
• Provident Fund
• Performance bonus
• Yearly bonus